Positional Encoder Graph Neural Networks for Geographic Data

• URL: http://arxiv.org/abs/2111.10144v1
• Date: Fri, 19 Nov 2021 10:41:49 GMT
• Title: Positional Encoder Graph Neural Networks for Geographic Data
• Authors: Konstantin Klemmer, Nathan Safir, Daniel B Neill
• Abstract summary: Graph neural networks (GNNs) provide a powerful and scalable solution for modeling continuous spatial data. In this paper, we propose PE-GNN, a new framework that incorporates spatial context and correlation explicitly into the models.
• Score: 1.840220263320992
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) provide a powerful and scalable solution for modeling continuous spatial data. However, in the absence of further context on the geometric structure of the data, they often rely on Euclidean distances to construct the input graphs. This assumption can be improbable in many real-world settings, where the spatial structure is more complex and explicitly non-Euclidean (e.g., road networks). In this paper, we propose PE-GNN, a new framework that incorporates spatial context and correlation explicitly into the models. Building on recent advances in geospatial auxiliary task learning and semantic spatial embeddings, our proposed method (1) learns a context-aware vector encoding of the geographic coordinates and (2) predicts spatial autocorrelation in the data in parallel with the main task. On spatial regression tasks, we show the effectiveness of our approach, improving performance over different state-of-the-art GNN approaches. We also test our approach for spatial interpolation, i.e., spatial regression without node features, a task that GNNs are currently not competitive at. We observe that our approach not only vastly improves over the GNN baselines, but can match Gaussian processes, the most commonly utilized method for spatial interpolation problems.

Related papers

• Cybercrime Prediction via Geographically Weighted Learning [0.24578723416255752]
  We propose a graph neural network model that accounts for geographical latitude and longitudinal points. Using a synthetically generated dataset, we apply the algorithm for a 4-class classification problem in cybersecurity. We demonstrate that it has higher accuracy than standard neural networks and convolutional neural networks.
  arXiv  Detail & Related papers  (2024-11-07T11:46:48Z)
• Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting [70.66710698485745]
  We propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting. AHSTN exploits the spatial hierarchy and modeling multi-scale spatial correlations. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.
  arXiv  Detail & Related papers  (2023-06-15T14:50:27Z)
• Localised Adaptive Spatial-Temporal Graph Neural Network [17.707594255626216]
  Adaptive Graph Sparsification (AGS) is a graph sparsification algorithm which successfully enables the localisation of ASTGNNs to an extreme extent. We observe that spatial graphs in ASTGNNs can be sparsified by over 99.5% without any decline in test accuracy. Localisation of ASTGNNs holds the potential to reduce the heavy overhead required on large-scale spatial-temporal data.
  arXiv  Detail & Related papers  (2023-06-12T08:08:53Z)
• Neural networks for geospatial data [0.0]
  NN-GLS is a new neural network estimation algorithm for the non-linear mean in GP models. We show that NN-GLS admits a representation as a special type of graph neural network (GNN) Theoretically, we show that NN-GLS will be consistent for irregularly observed spatially correlated data processes.
  arXiv  Detail & Related papers  (2023-04-18T17:52:23Z)
• Deep Spatial Domain Generalization [8.102110157532556]
  We develop the spatial graph neural network that handles spatial data as a graph and learns the spatial embedding on each node. The proposed method infers the spatial embedding of an unseen location during the test phase and decodes the parameters of the downstream-task model directly on the target location.
  arXiv  Detail & Related papers  (2022-10-03T06:16:20Z)
• pathGCN: Learning General Graph Spatial Operators from Paths [9.539495585692007]
  We propose pathGCN, a novel approach to learn the spatial operator from random paths on the graph. Our experiments on numerous datasets suggest that by properly learning both the spatial and point-wise convolutions, phenomena like over-smoothing can be inherently avoided.
  arXiv  Detail & Related papers  (2022-07-15T11:28:11Z)
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [72.16255675586089]
  We propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T07:18:57Z)
• Local Augmentation for Graph Neural Networks [78.48812244668017]
  We introduce the local augmentation, which enhances node features by its local subgraph structures. Based on the local augmentation, we further design a novel framework: LA-GNN, which can apply to any GNN models in a plug-and-play manner.
  arXiv  Detail & Related papers  (2021-09-08T18:10:08Z)
• Policy-GNN: Aggregation Optimization for Graph Neural Networks [60.50932472042379]
  Graph neural networks (GNNs) aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. We propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process.
  arXiv  Detail & Related papers  (2020-06-26T17:03:06Z)
• Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case [93.37576644429578]
  Graph neural networks (GNNs) have made great progress recently on learning from graph-structured data in practice. We provide a theoretically-grounded generalizability analysis of GNNs with one hidden layer for both regression and binary classification problems.
  arXiv  Detail & Related papers  (2020-06-25T00:45:52Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.